Authorship identification technique on basis of support vector machine

Download article in PDF format

Authors: Romanov A. S.

Annotation: In the article authorship identification problem in the case of the limited set of alternatives is posed as classification task. It is suggested to use support vector machine and text's N-gramm features for solving the problem. Classification accuracy improving based on smoothing techniques is considered. Results of experiments that confirm theoretical assumptions are given.

Keywords: authorship identification, classifire, text features, support vector machine, smoothing

Editorial office address

Executive Secretary of the Editor’s Office

 Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia

  Phone / Fax: + 7 (3822) 701-582

  journal@tusur.ru

 

Viktor N. Maslennikov

Executive Secretary of the Editor’s Office

 Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia

  Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02

  vnmas@tusur.ru

Subscription for updates